Method and device for predicting hydrogen content in refined wax oil

Abstract

The invention provides a method and device for predicting the hydrogen content in refined wax oil. The method comprises the following steps: acquiring related raw material parameters and operation parameters of a raw material wax oil sample; comparing the raw material parameters with a preset range, determining the raw material wax oil samples within the preset range as in-boundary samples, and determining the raw material wax oil samples outside the preset range as out-boundary samples; under the condition that the raw material wax oil sample is determined as an in-boundary sample, inputting raw material parameters and operation parameters into a wax oil hydrogen content prediction model so as to predict the refined wax oil hydrogen content of the raw material wax oil sample; and predicting the refined wax oil hydrogen content of the raw material wax oil sample according to the raw material parameter input and the hydrogen atom material balance function under the condition that the material wax oil sample is determined as an out-of-bound sample. Therefore, extrapolation and internal delay of the data model are taken into consideration, and the problem of large prediction error of the data model to the out-of-bound sample is solved under the condition that the modeling data volume is small.

Description

Technical Field

[0001] The present application relates to the field of chemical engineering, and in particular to a method and device for predicting the hydrogen content in refined wax oil, and a machine-readable storage medium. Background Art

[0002] There are many ways to save energy and reduce carbon emissions in refineries, including water saving, electricity saving, gas / steam saving, wind saving, etc. Among them, reducing hydrogen consumption has become a focus of refinery managers. Hydrogen consumption mainly comes from chemical reactions. Therefore, from the perspective of reducing carbon emissions at the source of chemical reactions, efficient use of hydrogen has become an important measure for energy conservation and carbon reduction.

[0003] As an important raw material pretreatment process, wax oil hydrogenation plays a significant role in improving the raw material parameters of catalytic cracking or hydrocracking. The main reactions in which hydrogen participates in the wax oil hydrogenation process include hydrodesulfurization, hydrodenitrogenation, hydrodeoxygenation, olefin saturation, aromatic saturation, etc., and these reactions are carried out on different catalysts. By establishing a pilot evaluation model for the catalyst and roughly calculating the hydrogen consumption of the actual industrial production unit based on the amplification effect, it is undoubtedly an effective tool to solve this problem. Summary of the invention

[0004] The inventors of the present application have found that due to the small amount of catalyst pilot evaluation data, the established data model (for example, the wax oil hydrogen content prediction model) is prone to the problem of good interpolation effect and poor extrapolation effect. Therefore, it is very important to adopt different methods to ensure the prediction effect of the model according to the characteristics of the new test data set. The present invention divides the value range of the relevant raw material parameters of the raw wax oil sample, and designs prediction schemes for in-bound and out-of-bound samples respectively. When the amount of modeling data is small, the prediction effect of the data model on out-of-bound samples is significantly improved.

[0005] In order to achieve the above-mentioned objectives, the first aspect of the present application provides a method for predicting the hydrogen content in refined wax oil, comprising: obtaining relevant raw material parameters of a raw wax oil sample and operating parameters of an operation applied to the raw wax oil sample for preparing refined wax oil; comparing the raw material parameters with a preset range, determining the raw wax oil sample within the preset range as an in-bounds sample, and determining the raw wax oil sample outside the preset range as an out-of-bounds sample; when the raw wax oil sample is determined to be an in-bounds sample, inputting the raw material parameters and operating parameters into a wax oil hydrogen content prediction model to predict the refined wax oil hydrogen content of the raw wax oil sample; and when the raw wax oil sample is determined to be an out-of-bounds sample, predicting the refined wax oil hydrogen content of the raw wax oil sample based on the raw material parameters and the hydrogen atom material balance function.

[0006] In the embodiments of the present application,

[0007]

[0008] In the embodiment of the present application, the preset range is based on the range of raw material parameters of the raw wax oil sample used in the modeling process of the wax oil hydrogen content prediction model.

[0009] In the embodiment of the present application, the hydrogen atom material balance function includes a functional relationship expression and corresponding constraints.

[0010] In the embodiment of the present application, the functional relationship expression is:

[0011]

[0012] Among them, H1% represents the hydrogen content in the raw wax oil, H2% represents the hydrogen content in the refined wax oil, S1% represents the sulfur content in the raw wax oil, and S2% represents the sulfur content in the refined wax oil; N1% represents the nitrogen content in the raw wax oil, and N2% represents the nitrogen content in the refined wax oil; δ(H) represents the equivalent hydrogen content loss due to olefin saturation, aromatic saturation and deoxidation; 32 represents the atomic weight of sulfur removal, and 12 represents the atomic weight of sulfide hydrogenation; 14 represents the atomic weight of nitrogen removal, and 7 represents the atomic weight of nitride hydrogenation.

[0013] In the embodiment of the present application, it is initially assumed that δ(H) is zero, and the hydrogen content H2% of the refined wax oil is calculated using the functional relationship expression. When the hydrogen content H2% of the refined wax oil does not satisfy the following constraints, the correction term δ(H) is determined according to the following constraints, and the correction term δ(H) is substituted into the functional relationship expression to recalculate the hydrogen content H2% of the refined wax oil as the predicted hydrogen content of the refined wax oil.

[0014] Constrain condition 0.8%≤(H2%-H1%)≤1.2%

[0015]

[0016] In an embodiment of the present application, the raw material parameters include one or more of the following: density, distillation range, S content, N content, carbon content, and hydrogen content.

[0017] In the embodiments of the present application, the operating parameters include one or more of the following: reaction pressure, reaction temperature, space velocity, and hydrogen-to-oil ratio.

[0018] A second aspect of the present application provides a device for predicting the hydrogen content in refined wax oil, the device comprising: a memory; and a processor, wherein the processor is configured to predict the hydrogen content in refined wax oil using the above method.

[0019] A third aspect of the present application provides a machine-readable storage medium having instructions stored thereon, which, when executed by a processor, configure the processor to execute the above-mentioned method for predicting the hydrogen content in refined wax oil.

[0020] A fourth aspect of the present application provides a computer program product, comprising a computer program, which, when executed by a processor, causes the processor to be configured to execute the above-mentioned method for predicting the hydrogen content in refined wax oil.

[0021] Through the above technical solution, the standard for dividing the new test data set into in-bounds test samples and out-bounds test samples is set; if the raw wax oil sample to be predicted is an in-bounds test sample, the trained model prediction result is directly used; if the raw wax oil sample to be predicted is an out-bounds test sample, the newly designed hydrogen atom material balance function is used for calculation to replace the model test result. In this way, the extrapolation and internal extension of the data model are taken into account, and the problem of large prediction errors of the data model for out-of-bounds samples is solved when the amount of modeling data is small.

[0022] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0024] Figure 1 The flowchart of the method for predicting the hydrogen content in refined wax oil according to an embodiment of the present application is schematically shown.

[0025] Figure 2 The flowchart of a method for predicting the hydrogen content in refined wax oil according to another embodiment of the present application is schematically shown.

[0026] Figure 3 The figure is a comparison chart of the predicted values ​​and measured values ​​of the out-of-bounds samples of the new test data set.

[0027] Figure 4 This is a comparison chart of the calculated values ​​and measured values ​​of out-of-bounds samples of the new test data set according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0029] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0030] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0031] It should be noted that the terms “features”, “feature variables”, and “input parameters” appear many times in this case. These terms can represent the features of the “data prediction model” used to predict the “output parameters” based on the “input parameters” and can be used interchangeably. In addition, the terms “model”, “data prediction model”, and “data-driven model” appear many times in this case and can be used interchangeably.

[0032] Figure 1 The schematic diagram of the process of predicting the hydrogen content in refined wax oil according to the embodiment of the present application is shown schematically. Figure 1 As shown, in one embodiment of the present application, a method for predicting the hydrogen content in refined wax oil is provided, the method comprising the following steps:

[0033] Step S110, obtaining relevant raw material parameters of the raw wax oil sample and operation parameters of the operation applied to the raw wax oil sample for preparing refined wax oil.

[0034] The raw material parameters here may include one or more of the following: density, distillation range, S content, N content, carbon content, and hydrogen content. The operating parameters may include one or more of the following: reaction pressure, reaction temperature, space velocity, and hydrogen-to-oil ratio. Of course, the present invention is not limited thereto and may include other raw material parameters and operating parameters in addition to the raw material parameters and operating parameters listed here.

[0035] Step S120, comparing the raw material parameters with a preset range, determining the raw material wax oil samples within the preset range as in-boundary samples, and determining the raw material wax oil samples outside the preset range as out-of-boundary samples.

[0036] The preset range can be determined based on the range of raw material parameters of the raw wax oil sample used in the modeling process of the following wax oil hydrogen content prediction model. For example, the preset range should be within the range of raw material parameters of the raw wax oil sample used in the modeling process of the wax oil hydrogen content prediction model.

[0037] Specifically, when all raw material parameters of the raw wax oil sample are within the preset range corresponding to the parameter, the raw wax oil sample is regarded as an in-bounds sample, otherwise the raw wax oil sample is regarded as an out-of-bounds sample. The specific expression of this judgment is as follows:

[0038]

[0039] Step S130, when the raw wax oil sample is determined to be an in-bounds sample, the raw material parameters and the operating parameters are input into a wax oil hydrogen content prediction model to predict the refined wax oil hydrogen content of the raw wax oil sample. The establishment process of the wax oil hydrogen content prediction model will be described later.

[0040] Step S140, when the raw wax oil sample is determined to be an out-of-bounds sample, predicting the refined wax oil hydrogen content of the raw wax oil sample according to the raw material parameters and the hydrogen atom material balance function.

[0041] Figure 1 FIG. 1 is a flow chart of a feature selection method for a data prediction model in one embodiment. It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0042] Through the above technical solution, the standard for dividing the new test data set into in-bounds test samples and out-bounds test samples is set; if the raw wax oil sample to be predicted is an in-bounds test sample, the trained model prediction result is directly used; if the raw wax oil sample to be predicted is an out-bounds test sample, the newly designed hydrogen atom material balance function is used for calculation to replace the model test result. In this way, the extrapolation and internal extension of the data model are taken into account, and the problem of large prediction errors of the data model for out-of-bounds samples is solved when the amount of modeling data is small.

[0043] Figure 2 The following schematically shows a flow chart of a method for predicting the hydrogen content in refined wax oil according to another embodiment of the present application. Figure 2 As shown, its general content is similar to Figure 1 , but it reflects the specific form of the material balance function of hydrogen atoms.

[0044] Specifically, the hydrogen atom material balance function includes a functional relationship expression and corresponding constraints, and the functional relationship expression is:

[0045]

[0046] Among them, H1% represents the hydrogen content in the raw wax oil, H2% represents the hydrogen content in the refined wax oil, S1% represents the sulfur content in the raw wax oil, and S2% represents the sulfur content in the refined wax oil; N1% represents the nitrogen content in the raw wax oil, and N2% represents the nitrogen content in the refined wax oil; δ(H) represents the equivalent hydrogen content loss of olefin saturation, aromatic saturation and deoxidation; 32 represents the atomic weight of sulfur removal, and 12 represents the atomic weight of sulfide hydrogenation; 14 represents the atomic weight of nitrogen removal, and 7 represents the atomic weight of nitride hydrogenation. Among them, the refined wax oil sulfur content represented by S2% and the refined wax oil nitrogen content represented by N2% can be predicted by using the corresponding refined wax oil sulfur and nitrogen content prediction model, or can be obtained by other methods. The refined wax oil sulfur and nitrogen content prediction model can be modeled similarly to the wax oil hydrogen content prediction model.

[0047] In the initial prediction of the refined wax oil hydrogen content of the raw wax oil sample, it can be assumed that δ(H) is zero, and the refined wax oil hydrogen content H2% is calculated using the functional relationship expression. When the refined wax oil hydrogen content H2% does not meet the following constraints, the correction term δ(H) is determined according to the following constraints, and the correction term δ(H) is substituted into the above functional relationship expression to recalculate the refined wax oil hydrogen content H2% as the final predicted refined wax oil hydrogen content.

[0048] Constrain condition 0.8%≤(H2%-H1%)≤1.2%

[0049]

[0050] Of course, specific functional formulas and constraints as well as the numerical ranges of these constraints are given here. Appropriate deformation of these functional formulas and constraints should also be considered to be within the scope of protection of this case.

[0051] Based on the shortcomings of small data models for brand new test data, the interpolation effect is ideal but the epitaxial effect is poor, the present invention proposes a new method to solve the problem of poor epitaxial effect of small data models. The first step is to collect the pilot evaluation data of a catalyst for wax oil hydrogenation to establish a data-driven model. The second step is to determine the value range of each parameter of the modeling input item raw material. The third step is to judge the value range of the raw material parameters of the brand new test data set. If it is within the value range of the raw material parameters of the modeling data, it is an in-bounds sample. If it is outside its value range, it is an out-of-bounds sample. The fourth step is to design a refined wax oil hydrogen content function. The fifth step is to use the model prediction if the new test data set is judged as an in-bounds sample; if it is judged as an out-of-bounds sample, use the function calculation.

[0052] For data models, when facing new test data, users hope that it has a certain interpolation effect and a certain extension. The model built by small data itself has a certain interpolation effect, but the extension effect is poor. By dividing the new test data set into in-bounds samples and out-of-bounds samples, different solutions are designed to make the practical application of small data models possible.

[0053] The present invention uses the deep learning framework Keras to build the model. Keras is a deep learning framework for building models and an advanced neural network application programming interface written in Python. It consists of a series of independent and fully configurable modules that can be assembled together according to actual needs. In particular, the neural network layer, loss function, optimizer, initialization method, activation function, and regularization method are all modules that can be combined to build the model.

[0054] When building the model, python is used to write the model code, and the deep learning framework Keras is called to build the model. The training of the model requires calling the input and output features and data in Excel respectively. The input features are mainly divided into two parts: raw material parameters and operating parameters. Among them, the raw material parameters include: raw material density, raw material S content, raw material N content, carbon content, hydrogen content, raw material distillation range (IBP, 10%, 30%, ..., FBP) and other characteristics, and the operating parameters include: reaction temperature, reaction pressure, space velocity, hydrogen-to-oil ratio. The output parameter is the hydrogen content of refined wax oil. If the above-mentioned refined wax oil sulfur and nitrogen content prediction model is established, the output parameters can be the corresponding refined wax oil sulfur and nitrogen content.

[0055] The features and data corresponding to the input and output are cleaned, and the features and data of the input and output are kept in one-to-one correspondence as much as possible, and are organized in Excel tables for easy reading by the algorithm program. All data are randomly divided into training set, validation set and test set in a ratio of 8:1:1. The training set data is used for model training, the validation set is used for model hyperparameter optimization, and the test set is used to test the model prediction effect. The evaluation indicators of the model are mean absolute error (MAE), mean relative error (MRE) and determination coefficient R 2 The relevant statistical parameters required to establish the model are as follows, among which,

[0056]

[0057]

[0058]

[0059] In the above formula, n is the number of test set samples, y i,actual represents the sample measured value, y i,predicted Represents the sample prediction value, MAE reflects the degree to which all sample prediction values ​​deviate from the true value, MRE reflects the credibility of all sample prediction results, R 2 It reflects the degree of fit between the model prediction value and the true value.

[0060] If the new test data is judged to be an in-bounds sample, the trained model is used to predict the new test data. If the new test data is judged to be an out-of-bounds sample, the newly designed function calculation method is used.

[0061] The present invention is further described in detail below by examples, but the present invention is not limited thereto.

[0062] (1) The collected data on the evaluation of the pilot catalyst for wax oil hydrogenation were sorted out and all the data were divided into two parts: input and output. The input data included: raw material parameters (density, distillation range, S content, N content, etc.), operating parameters (reaction pressure, reaction temperature, space velocity, hydrogen-oil ratio); the output data was the hydrogen content of the refined wax oil.

[0063] (2) All data are divided into two parts, one part is used for modeling, and the modeling data set is divided into a training set, a validation set and a test set in a ratio of 8:1:1. The training set is used to train the model, the validation set is used to determine the hyperparameters of the model, and the test set is used to verify the model effect. The other part of the array is used to make a new test data set, which is used to compare the refined wax oil hydrogen content determined by the embodiment of the present invention with the refined wax oil hydrogen content predicted by the model in the comparative example.

[0064] (3) Use Python to write programs, build a deep learning framework, and establish a prediction model M1 for the sulfur content of hydrogenated wax oil.

[0065] (4) Rules for determining the value range of raw material parameters in the new test data set. If the value range of a parameter is within the value range of the raw material parameters of the modeling data, it is determined to be an in-bounds sample (all parameters must meet the requirements); if the new test data is outside the value range of the raw material parameters of the modeling data, it is determined to be an out-of-bounds sample.

[0066] (5) Calculate the value range of each parameter of the raw materials in all modeling data sets. These parameters include raw material density, sulfur content, nitrogen content, distillation range, etc. Suppose the value range of the i-th parameter in the raw material parameters is Ci (min) ≤Ci≤Ci (max) , the minimum value is Ci (min) , the maximum value is Ci (max) .

[0067] (6) The new data set to be tested is divided into in-bounds samples and out-bounds samples. Assume that the value of a parameter in the raw material parameters of the new data set to be tested is Ci′, and the corresponding in-bounds sample and out-bounds sample discrimination expression is as shown in formula (1).

[0068]

[0069] (7) If the array in the new test data set is judged as an in-bounds sample, model M1 is used to make predictions directly;

[0070] (8) If the array in the new test data set is judged as an out-of-bounds sample, an implementation example and a comparative example are designed.

[0071] (9) According to the embodiment, a method for calculating the hydrogen content of the hydrogenated wax oil of the out-of-bounds sample is designed. The design of the calculation function relationship of the hydrogen content is based on the hydrogen balance calculation from the raw material to the product. The impurities such as sulfur, nitrogen, and oxygen removed during the reaction are converted into the removal of hydrogen, and the part of the aromatic saturation and olefin saturation hydrogenation is converted into the addition of hydrogen. According to the material balance of the hydrogen element, the newly designed function expression is as shown in formula (2).

[0072]

[0073] Among them, H1% represents the hydrogen content in the raw wax oil, H2% represents the hydrogen content in the refined wax oil product, S1% represents the sulfur content in the raw wax oil, S2% represents the sulfur content in the refined wax oil product (for example, the sulfur content predicted by the refined wax oil sulfur content prediction model); N1% represents the nitrogen content in the raw wax oil, N2% represents the nitrogen content in the refined wax oil product (for example, the nitrogen content predicted by the refined wax oil nitrogen content prediction model); δ(H) represents the equivalent hydrogen content loss of olefin saturation, aromatic saturation and deoxidation; 32 represents the atomic weight of sulfur removal, and 12 represents the atomic weight of sulfide hydrogenation; 14 represents the atomic weight of nitrogen removal, and 7 represents the atomic weight of nitride hydrogenation.

[0074] (10) For the embodiment, the value standard of δ(H) is set. According to process experience, the increase in hydrogen consumption has a certain range. If the result calculated by the functional relationship is outside the range, δ(H) should be introduced as a correction term, and the corresponding constraint conditions and the value of δ(H) are set. If the result calculated by the functional relationship is within the range, δ(H) takes an equivalent infinitesimal value (for example, 0), as shown in Formula (3).

[0075] Constrain condition 0.8%≤(H2%-H1%)≤1.2%

[0076]

[0077] Before applying the constraints, δ(H) is taken as an equivalent infinitesimal (for example, 0), and based on this and the above functional formula (2), H2% is calculated. Subsequently, the H2% and H1% are substituted into the above constraints (3), δ(H) is re-determined, and based on the re-determined δ(H) and the above functional formula (2), H2% is recalculated, and the H2% is used as the predicted hydrogen content in the refined wax oil product.

[0078] (11) The embodiment method is to calculate the value of the hydrogen content of the refined wax oil by the new out-of-bounds sample function relationship expression. The difference between this value and the measured value is as follows: Figure 3 The proportional method is the predicted value obtained by model M1 for out-of-bounds samples. The difference between the predicted value and the measured value is shown in Figure 2The value of the hydrogen content of refined wax oil calculated by the new design function expression is compared with the value of the hydrogen content of refined wax oil predicted by the model M1 in the comparative example.

[0079] In order to compare the difference between the embodiment and the comparative example in predicting the new test array, the measured value, the comparative example predicted value, the embodiment calculated value, the difference between the comparative example and the measured value, and the difference between the embodiment and the measured value are listed respectively. The detailed results are shown in Table 1, where the difference 1 represents the difference between the comparative example predicted value and the measured value, and the difference 2 represents the difference between the embodiment calculated value and the measured value. After comparison, it is found that for the new out-of-bounds samples, the calculated value of the refined wax oil hydrogen content in the new test array by the newly designed function expression is obviously closer to the measured value, and the deviation is within 0.1%, which illustrates the effectiveness of the embodiment method.

[0080] Table 1 Comparison of prediction effects of the embodiment and the comparative example on the new test array

[0081]

[0082]

[0083] After comparison, it is found that the prediction error of the newly set function expression of the hydrogen content of refined wax oil in the embodiment for out-of-bounds samples is significantly lower than the prediction error of the model in the comparative example for out-of-bounds samples, which fully demonstrates the effectiveness of this method.

[0084] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0085] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0086] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0087] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0088] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0089] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0090] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0091] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0092] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for predicting the hydrogen content in refined gas oil, comprising: Obtaining relevant raw material parameters of the raw wax oil sample and operating parameters applied to the raw wax oil sample for preparing refined wax oil; Comparing the raw material parameter with a preset range, determining the raw material wax oil sample within the preset range as an in-bounds sample, and determining the raw material wax oil sample outside the preset range as an out-bounds sample; When the raw wax oil sample is determined to be an in-bounds sample, the raw material parameters and the operating parameters are input into a wax oil hydrogen content prediction model to predict the refined wax oil hydrogen content of the raw wax oil sample; as well as When the raw wax oil sample is determined to be an out-of-bounds sample, the hydrogen content of the refined wax oil of the raw wax oil sample is predicted based on the raw material parameters and the hydrogen atom material balance function.

2. The method according to claim 1, wherein:

3. The method according to claim 1, wherein: The preset range is based on the range of raw material parameters of the raw wax oil sample used in the modeling process of the wax oil hydrogen content prediction model.

4. The method according to claim 1, wherein: The hydrogen atom material balance function includes a functional relationship expression and corresponding constraints.

5. The method according to claim 4, wherein: The functional relationship expression is: Among them, H1% represents the hydrogen content in the raw wax oil, H2% represents the hydrogen content in the refined wax oil, S1% represents the sulfur content in the raw wax oil, and S2% represents the sulfur content in the refined wax oil; N1% represents the nitrogen content in the raw wax oil, and N2% represents the nitrogen content in the refined wax oil; δ(H) represents the equivalent hydrogen content loss due to olefin saturation, aromatic saturation and deoxidation; 32 represents the atomic weight of sulfur removal, and 12 represents the atomic weight of sulfide hydrogenation; 14 represents the atomic weight of nitrogen removal, and 7 represents the atomic weight of nitride hydrogenation.

6. The method according to claim 5, wherein: Initially assuming that δ(H) is zero, the hydrogen content H2% of the refined wax oil is calculated using the functional relationship expression. When the hydrogen content H2% of the refined wax oil does not satisfy the following constraints, the correction term δ(H) is determined according to the following constraints, and the correction term δ(H) is substituted into the functional relationship expression to recalculate the hydrogen content H2% of the refined wax oil as the predicted hydrogen content of the refined wax oil. Constraincondition0.8%≤(H2%-H1%)≤1.2% 7. The method according to any one of claims 1 to 6, wherein: The feedstock parameters include one or more of the following: density, distillation range, S content, N content, carbon content, and hydrogen content.

8. The method according to any one of claims 1 to 6, wherein: The operating parameters include one or more of the following: reaction pressure, reaction temperature, space velocity, and hydrogen-to-oil ratio.

9. A device for predicting the hydrogen content in refined gas oil, characterized in that: The device comprises: Memory; and A processor, the processor being configured to execute the method for predicting the hydrogen content in refined gas oil according to any one of claims 1 to 8.

10. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to execute the method for predicting the hydrogen content in refined gas oil according to any one of claims 1 to 8.

Images